Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3033 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.1920. Min Range: -2.1920

Max Act: 2.1920. Min Act: -0.0002

Data Index: 794622 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.9582. Min Act: -0.0002

Data Index: 497033 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.9057. Min Act: -0.0002

Data Index: 646942 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.8184. Min Act: -0.0002

Data Index: 1041063 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.8010. Min Act: -0.0002

Data Index: 627881 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.8219. Min Act: -0.0002

Data Index: 101951 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.8345. Min Act: -0.0002

Data Index: 476210 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7807. Min Act: -0.0002

Data Index: 955642 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7799. Min Act: -0.0002

Data Index: 585439 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7336. Min Act: -0.0003

Data Index: 1339500 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7922. Min Act: -0.0003

Data Index: 1036897 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7676. Min Act: -0.0002

Data Index: 198094 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7332. Min Act: -0.0002

Data Index: 1242736 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7415. Min Act: -0.0002

Data Index: 155778 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7007. Min Act: -0.0002

Data Index: 541275 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7590. Min Act: -0.0003

Data Index: 1055557 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7055. Min Act: -0.0002

Data Index: 909422 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.6964. Min Act: -0.0002

Data Index: 674248 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.6904. Min Act: -0.0003

Data Index: 776427 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 2.1920. Min Range: -2.1920

Max Act: 1.7485. Min Act: -0.0002

Data Index: 1303406 (C4 (Web Text))

Max Activating Token Index: 913